Config validation error

[Teeesa7]

Hi everyone,

I recently generated my train.spacy and dev.spacy files and proceeded to use the spaCy widget to assist in creating my config file. However, when I attempt to start training with this configuration, I encounter errors.

The errors specifically mention issues with the optimizer, tokenizer, and vectors, despite following the widget's guidance for setting up these components. Here's my configuration file and the errors I'm facing:

config.cfg:

[paths]
train = spacy_split_output/train.spacy
dev = spacy_split_output/dev.spacy
vectors = "en_core_web_lg"
init_tok2vec = null

[system]
gpu_allocator = null
seed = 0

[nlp]
lang = "en"
pipeline = ["transformer","ner"]
batch_size = 128
disabled = []
before_creation = null
after_creation = null
after_pipeline_creation = null
tokenizer = {"@tokenizers": "spacy.Tokenizer.v1"}
vectors = {"@vectors": "spacy.Vectors.v1"}

[components]

[components.ner]
factory = "ner"
incorrect_spans_key = null
moves = null
scorer = {"@scorers":"spacy.ner_scorer.v1"}
update_with_oracle_cut_size = 100

[components.ner.model]
@architectures = "spacy.TransitionBasedParser.v2"
state_type = "ner"
extra_state_tokens = false
hidden_width = 64
maxout_pieces = 2
use_upper = true
nO = null

[components.ner.model.tok2vec]
@architectures = "spacy.Tok2VecListener.v1"
width = ${components.tok2vec.model.encode.width}
upstream = "*"

[components.tok2vec]
factory = "tok2vec"

[components.tok2vec.model]
@architectures = "spacy.Tok2Vec.v2"

[components.tok2vec.model.embed]
@architectures = "spacy.MultiHashEmbed.v2"
width = ${components.tok2vec.model.encode.width}
attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
rows = [5000,1000,2500,2500]
include_static_vectors = true

[components.tok2vec.model.encode]
@architectures = "spacy.MaxoutWindowEncoder.v2"
width = 256
depth = 8
window_size = 1
maxout_pieces = 3

[corpora]

[corpora.dev]
@readers = "spacy.Corpus.v1"
path = ${paths.dev}
max_length = 0
gold_preproc = false
limit = 0
augmenter = null

[corpora.train]
@readers = "spacy.Corpus.v1"
path = ${paths.train}
max_length = 0
gold_preproc = false
limit = 0
augmenter = null

[training]
dev_corpus = "corpora.dev"
train_corpus = "corpora.train"
seed = ${system.seed}
gpu_allocator = ${system.gpu_allocator}
dropout = 0.1
accumulate_gradient = 1
patience = 1600
max_epochs = 0
max_steps = 20000
eval_frequency = 200
frozen_components = []
annotating_components = []
before_to_disk = null
before_update = null

[training.batcher]
@batchers = "spacy.batch_by_words.v1"
discard_oversize = false
tolerance = 0.2
get_length = null

[training.batcher.size]
@schedules = "compounding.v1"
start = 100
stop = 1000
compound = 1.001
t = 0.0

[training.logger]
@loggers = "spacy.ConsoleLogger.v1"
progress_bar = false

[training.optimizer]
@optimizers = "spacy.optimizer.Adam.v1"
beta1 = 0.9
beta2 = 0.999
L2_is_weight_decay = true
L2 = 0.01
grad_clip = 1.0
use_averages = false
eps = 0.00000001
learn_rate = 0.001

[training.score_weights]
ents_f = 1.0
ents_p = 0.0
ents_r = 0.0
ents_per_type = null

[pretraining]

[initialize]
vectors = ${paths.vectors}
init_tok2vec = ${paths.init_tok2vec}
vocab_data = null
lookups = null
before_init = null
after_init = null

[initialize.components]

[initialize.tokenizer]

After running python -m spacy train config.cfg --output ./output, I get:

ℹ Saving to output directory: output
ℹ Using CPU

=========================== Initializing pipeline ===========================
✘ Config validation error
training -> optimizer   instance of Optimizer expected
nlp -> tokenizer        Promise(registry='tokenizers', name='spacy.Tokenizer.v1', args=[], kwargs={}) is not callable
nlp -> vectors  Promise(registry='vectors', name='spacy.Vectors.v1', args=[], kwargs={}) is not callable       
{'components': {}, 'corpora': {'dev': {'@readers': 'spacy.Corpus.v1', 'path': 'spacy_split_output/dev.spacy', 'max_length': 0, 'gold_preproc': False, 'limit': 0, 'augmenter': None}, 'train': {'@readers': 'spacy.Corpus.v1', 'path': 'spacy_split_output/train.spacy', 'max_length': 0, 'gold_preproc': False, 'limit': 0, 'augmenter': None}}, 'initialize': {'vectors': 'en_core_web_lg', 'init_tok2vec': None, 'vocab_data': None, 'lookups': None, 'before_init': None, 'after_init': None, 'components': {}, 'tokenizer': {}}, 'nlp': {'lang': 'en', 'pipeline': ['transformer', 'ner'], 'batch_size': 128, 'disabled': [], 'before_creation': None, 'after_creation': None, 'after_pipeline_creation': None, 'tokenizer': {'@tokenizers': 'spacy.Tokenizer.v1'}, 'vectors': {'@vectors': 'spacy.Vectors.v1'}}, 'paths': {'train': 'spacy_split_output/train.spacy', 'dev': 'spacy_split_output/dev.spacy', 'vectors': 'en_core_web_lg', 'init_tok2vec': None}, 'system': {'gpu_allocator': None, 'seed': 0}, 'training': {'dev_corpus': 'corpora.dev', 'train_corpus': 'corpora.train', 'seed': 0, 'gpu_allocator': None, 'dropout': 0.1, 'accumulate_gradient': 1, 'patience': 1600, 'max_epochs': 0, 'max_steps': 20000, 'eval_frequency': 200, 'frozen_components': [], 'annotating_components': [], 'before_to_disk': None, 'before_update': None, 'batcher': {'@batchers': 'spacy.batch_by_words.v1', 'discard_oversize': False, 'tolerance': 0.2, 'get_length': None, 'size': {'@schedules': 'compounding.v1', 'start': 100, 'stop': 1000, 'compound': 1.001, 't': 0.0}}, 'logger': {'@loggers': 'spacy.ConsoleLogger.v1', 'progress_bar': False}, 'optimizer': {'@optimizers': 'spacy.optimizer.Adam.v1', 'beta1': 0.9, 'beta2': 0.999, 'L2_is_weight_decay': True, 'L2': 0.01, 'grad_clip': 1.0, 'use_averages': False, 'eps': 1e-08, 'learn_rate': 0.001}, 'score_weights': {'ents_f': 1.0, 'ents_p': 0.0, 'ents_r': 0.0, 'ents_per_type': None}}}

Could someone please advise on how to properly configure these components to resolve the errors?
Thanks alot!